# Kula Intelligence Docs ## Docs - [What Kula Intelligence is](https://docs.kula.digital/readme.md): AI that actually knows your studio — a shared, always-current view of the whole business, answered in plain English in the assistant you already use, scoped so each teammate sees only what they're all - [Set up & get your first answer](https://docs.kula.digital/get-started/start.md): The full setup, start to finish — no technical help needed. About 15 minutes to your first real answer. - [Run your first diagnostic](https://docs.kula.digital/get-started/first-diagnostic.md): Let the AI work up your whole studio in order — what's true first, what to do about it second. - [What you can ask](https://docs.kula.digital/get-started/ask.md): A library of plain-English questions grouped by the problem you're trying to solve — with what to expect back. - [Is my data safe?](https://docs.kula.digital/get-started/trust.md): The short, plain-English version of how we protect your studio's data — and where to read the detail. - [Your weekly rhythm](https://docs.kula.digital/get-started/your-rhythm.md): A simple habit that keeps Kula Intelligence useful long after setup — what to check, what to ask, and where things live. - [Connect Claude](https://docs.kula.digital/connect-claude-and-access/claude.md): Get a role-scoped connect link from app.kula.digital and add it to Claude. Access is always controlled by your rules — there's no direct, open connection. - [Permission levels](https://docs.kula.digital/connect-claude-and-access/scopes.md): How role-based access works — each connect link or access token is issued at a permission level that controls how much personal data the assistant can see. - [Troubleshooting](https://docs.kula.digital/connect-claude-and-access/troubleshooting.md): Common questions, the errors you might hit and what they mean, current limitations, and how to reach us. - [How connectors work](https://docs.kula.digital/your-data-sources/connectors.md): What a connector is, the sources you can connect, the simple Test → Connect → Import → Process rhythm they all share, and the gap analysis that tells you your data is complete. - [Stripe](https://docs.kula.digital/your-data-sources/stripe.md): Connect Stripe to bring in payments, subscriptions, and invoices — read-only. - [Wix](https://docs.kula.digital/your-data-sources/wix.md): Connect Wix to bring in bookings, members, pricing plans, and online-store orders — read-only. - [Xero](https://docs.kula.digital/your-data-sources/xero.md): Connect Xero to bring in your accounting — contacts, transactions, and the general ledger — read-only. - [Mindbody](https://docs.kula.digital/your-data-sources/mindbody.md): Connect Mindbody to bring in clients, memberships, classes, attendance, and sales — read-only. - [GymMaster](https://docs.kula.digital/your-data-sources/gymmaster.md): Connect GymMaster to bring in members, classes, attendance, and memberships — read-only. - [Meta — Facebook & Instagram](https://docs.kula.digital/your-data-sources/meta.md): Connect Meta to bring in your Facebook and Instagram marketing performance and ad spend — read-only. - [Google Analytics 4](https://docs.kula.digital/your-data-sources/ga4.md): Connect GA4 to bring in website traffic, sources, and conversions — aggregated, read-only. - [CSV & ClassPass](https://docs.kula.digital/your-data-sources/csv.md): Upload a spreadsheet — a Mindbody export, a member list, or a ClassPass reservations report — when there's no direct connection. - [Keeping your connectors healthy](https://docs.kula.digital/your-data-sources/operating.md): The one operating guide that applies to every connector — spotting data gaps, recovering when a provider fails, and the weekly glance that keeps everything flowing. - [What skills are](https://docs.kula.digital/skills/skills.md): Saved, repeatable playbooks the AI can run on your studio — the ones we ship, and the ones you build yourself. - [The built-in library](https://docs.kula.digital/skills/library.md): The free skills we ship with every studio, and how to run one. - [Studio Ignition](https://docs.kula.digital/skills/studio-ignition.md): The paid, staged diagnostic add-on from the Skills marketplace — add it once and your studio unlocks the full runbook plus the skill set that runs it against your data. - [Build your own & share with your team](https://docs.kula.digital/skills/build-your-own.md): Turn the way you analyse your studio into a reusable skill, then publish it so your whole team's AI runs it the same way. - [Helping a studio go faster](https://docs.kula.digital/for-consultants/consultants.md): For consultants — how to set a studio up, run the first diagnostic, and hand control back. Optional by design; the owner can do all of this themselves. - [Set up on their behalf](https://docs.kula.digital/for-consultants/set-up-on-their-behalf.md): Use a single-use connect link to set a studio up without the owner having to handle keys — while their data stays theirs. - [Facilitate the first diagnostic](https://docs.kula.digital/for-consultants/facilitate-the-diagnostic.md): Run Studio Ignition with the owner, and turn what it finds into a short list of early wins they can act on. - [Hand off cleanly](https://docs.kula.digital/for-consultants/hand-off.md): Leave the owner self-sufficient — a short leave-behind, the keys in their hands, and your own access revoked. - [Overview](https://docs.kula.digital/for-developers/overview.md): The technical shape of Kula Intelligence — a remote MCP server over per-studio Postgres, with OAuth and a curated tool surface. - [Connect — API, Code, Cursor, Lovable](https://docs.kula.digital/for-developers/connect.md): Connect non-OAuth AI clients with a role-scoped access token minted in app.kula.digital, which generates the ready-to-paste config for each platform. - [Build your own interface](https://docs.kula.digital/for-developers/build-your-own-interface.md): A developer guide to building a custom app or UI directly on the Kula Intelligence MCP — connection and scopes, execute\_query gotchas, the unified schema, and a worked reference implementation. - [Tool reference](https://docs.kula.digital/for-developers/tools.md): Every tool the Kula Intelligence MCP server exposes, with read-only/destructive flags and the minimum permission level. - [Schema reference](https://docs.kula.digital/for-developers/schema.md): The tables and columns behind the freeform query tools — schema families, the canonical column pattern, and how PII redaction works per permission level. - [Graph & relationship tools](https://docs.kula.digital/for-developers/graph.md): The relationship graph — member–staff–location edges, resilience scores, vulnerability quadrants and at-risk signals — and the purpose-scoped tools that read it. - [OAuth](https://docs.kula.digital/for-developers/oauth.md): How Kula Intelligence implements OAuth 2.1 for MCP clients — discovery, dynamic client registration, PKCE, scopes, and audience binding. - [Changelog & versioning](https://docs.kula.digital/for-developers/changelog.md): How the Kula Intelligence tool surface evolves, our compatibility promises, and notable changes. - [Security & data handling](https://docs.kula.digital/trust-and-legal/security.md): How Kula Intelligence protects your studio's data — isolation, encryption, access control, auditing, and what we deliberately don't do. - [Privacy policy](https://docs.kula.digital/trust-and-legal/privacy.md): How Kula Intelligence collects, uses, stores, shares, and retains data — what it deliberately never does — and your choices and rights. - [Terms of service](https://docs.kula.digital/trust-and-legal/terms.md): The terms governing use of Kula Intelligence — what the service is, your responsibilities, AI-output limits, what it never does, and the legal terms. - [Responsible disclosure](https://docs.kula.digital/trust-and-legal/disclosure.md): How to report a security vulnerability in Kula Intelligence. - [Reviewer guide](https://docs.kula.digital/reviewers/reviewers.md): For Anthropic connector reviewers — test-account access, every tool with an example prompt, the OAuth round-trip, and the isolation model. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on a page URL with the `ask` query parameter: ``` GET https://docs.kula.digital/readme.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.